Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning temporal probabilistic causal models from longitudinal data

A Riva1, R Bellazzi

  • 1Dipartimento di Informatica e Sistemistica, Università di Pavia, Italy.

Artificial Intelligence in Medicine
|July 1, 1996
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Breaking barriers in extensively drug-resistant TB: pretomanid-centred long regimen achieves cure in a bedaquiline-resistant strain.

IJTLD open·2026
Same author

Smart Socks for Gait Analysis: A Comparative Study of Algorithms.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Unilateral uveitis following adjuvanted Varicella-Zoster subunit vaccine in a patient with previously resolved Varicella Zoster acute retinal necrosis.

Journal of ophthalmic inflammation and infection·2025
Same author

Rifampicin drug monitoring in TB patients: new evidence for increased dosage?

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2025
Same author

<i>ARID1B</i>-related disorder in 87 adults: Natural history and self-sustainability.

Genetics in medicine open·2024
Same author

An AI-based approach driven by genotypes and phenotypes to uplift the diagnostic yield of genetic diseases.

Human genetics·2024
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

This study introduces a method for learning temporal causal models from longitudinal data using Causal Probabilistic Networks (CPNs). The approach effectively models complex physiological behaviors, demonstrated through diabetes monitoring.

Area of Science:

  • Computational Biology
  • Medical Informatics
  • Time Series Analysis

Background:

  • Longitudinal medical data analysis often requires structural models of physiological behavior.
  • Probabilistic models, specifically Causal Probabilistic Networks (CPNs), offer a robust framework for managing underspecified information in time-series data.

Purpose of the Study:

  • To propose and evaluate a method for structural learning of Causal Probabilistic Networks (CPNs) from longitudinal time-series data.
  • To demonstrate the application of this methodology in the domain of diabetes monitoring, modeling blood glucose levels based on insulin and meal intake.

Main Methods:

  • Utilized model selection for structural learning of CPNs representing time-series.
  • Applied a learning algorithm to extract conditional probabilities from incomplete longitudinal data.

Related Experiment Videos

  • Employed scoring functions based on one-step ahead predictions for ranking reconstructed time-series models.

    • Main Results:

    • Successfully extracted conditional probabilities and ranked models for time-series reconstruction.
    • Demonstrated the method's efficacy in a diabetes monitoring example, despite physiological non-linearities and data unreliability.
    • Obtained meaningful results in conditional probability learning and model ranking power.

    Conclusions:

    • The proposed methodology enables effective structural learning of Causal Probabilistic Networks for time-series data.
    • This approach provides a powerful tool for analyzing complex physiological systems and improving predictions in medical monitoring.
    • The method shows promise for applications with non-linear dynamics and unreliable data.